Researchers from the Technical University of Denmark (DTU), the University of Copenhagen, and Caltech have made a breakthrough in improving the capabilities of AI algorithms by incorporating taste. While wine apps like Vivino, Hello Vino, and Wine Searcher already use AI to help users select wines based on labels and reviews, the new study showed that integrating people’s flavor impressions into these algorithms enhances their precision in predicting individual taste preferences.
The researchers conducted tastings with 256 participants to analyze their flavor impressions and combined this data with hundreds of thousands of wine labels and user reviews from Vivino to develop an algorithm that incorporates the dimension of flavor. This development enables wine enthusiasts to find wines similar in taste or both taste and price to their favorites.
Thoranna Bender, a graduate student at DTU, highlighted the algorithm’s potential by stating that it allows users to find wines most similar to their favorites in taste or both taste and price. The study’s co-author and professor Serge Belongie from the University of Copenhagen emphasized the significance of using human sensory experiences in machine learning, resulting in improved algorithms for users. Incorporating taste as a data source in AI holds promise, particularly in the food sector.
Belongie also predicted increased research at the intersection of food science and AI, noting the importance of understanding taste for healthy, sustainable food production. He also suggested that the method could be applied to other types of food and beverages, such as beer and coffee. The researchers have made their data publicly available for further exploration and development, encouraging collaboration and expanding the dataset for broader applications.
The study’s findings have been published in arXiv, and the researchers hope that this development will lead to more accurate predictions of people’s taste preferences, benefiting users. This shift in AI technology represents a significant advancement in the intersection of AI and the food and beverage industry.
